Wasm Engine Zoo

Query Docs
NameTypeDescription
rawTableOriginal CSV data
runsTableIndividual successful runs (use for filtering)
failedTableFailed runs (return_code !== 0)
versionsTableEngine × version that produced the numbers (empty for older data)
benchmarksTablePer-engine, per-benchmark scores (repeats collapsed to their median)
scoresTableEngine × benchmark scores (ordered by total_score)
runtimesTableEngine × benchmark times in seconds (ordered by total)
computeScores(runs)FunctionCompute scores table from filtered runs
computeRuntimes(runs)FunctionCompute runtimes table from filtered runs
aqGlobalArquero library
opGlobalArquero operators

Scoring: Repeated runs of the same engine and benchmark are first collapsed to their median time — timings are right-skewed, since a run can be slowed by unrelated load but never made faster than the machine allows. For each benchmark, the geometric mean of those times across all engines is computed. An engine's score for a benchmark is gmean / time (faster = higher). Total score is the sum across benchmarks. The runs column records how many repeats each row summarizes.

Filter + Recompute Examples
// Exclude engines
(tables) => {
  const { runs, computeScores, computeRuntimes } = tables;
  const filtered = runs.filter(d => d.engine !== 'wasm3');
  return computeScores(filtered); // or computeRuntimes(filtered)
}

// Only specific benchmarks
(tables) => {
  const { runs, computeScores } = tables;
  const keep = ['coremark', 'meshoptimizer'];
  return computeScores(runs.filter(aq.escape(d => keep.includes(d.benchmark))));
}
Benchmark Info
OSUbuntu 24.04.4 LTS x86_64
Kernel6.8.0-38-generic
CPUIntel i7-14700K (28) @ 5.500GHz
RAM32 GB
(tables) => { const { runs, benchmarks, computeScores, computeRuntimes } = tables; return computeScores(runs); }
Loading data...